# Loading necessary library files
library(shiny)
library(tidyverse)
## Warning: package 'tidyverse' was built under R version 4.2.3
## Warning: package 'ggplot2' was built under R version 4.2.3
## Warning: package 'tibble' was built under R version 4.2.3
## Warning: package 'readr' was built under R version 4.2.3
## Warning: package 'dplyr' was built under R version 4.2.3
## Warning: package 'forcats' was built under R version 4.2.3
## Warning: package 'lubridate' was built under R version 4.2.3
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.1 ✔ readr 2.1.4
## ✔ forcats 1.0.0 ✔ stringr 1.5.0
## ✔ ggplot2 3.4.2 ✔ tibble 3.2.1
## ✔ lubridate 1.9.2 ✔ tidyr 1.3.0
## ✔ purrr 1.0.1
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the ]8;;http://conflicted.r-lib.org/conflicted package]8;; to force all conflicts to become errors
library(lubridate)
library(plotly)
## Warning: package 'plotly' was built under R version 4.2.3
##
## Attaching package: 'plotly'
##
## The following object is masked from 'package:ggplot2':
##
## last_plot
##
## The following object is masked from 'package:stats':
##
## filter
##
## The following object is masked from 'package:graphics':
##
## layout
library(leaflet)
library(leaflet.extras)
## Warning: package 'leaflet.extras' was built under R version 4.2.3
data <- read.csv("DataCoSupplyChainDataset.csv")
data <- subset(data, select = -c(Customer.Email, Customer.Password, Order.Item.Cardprod.Id, Order.Zipcode, Product.Card.Id, Product.Description, Product.Image))
data <- na.omit(data)
# Display summary statistics for numerical variables
summary(data[, c("Days.for.shipping..real.","Days.for.shipment..scheduled.","Benefit.per.order","Sales.per.customer")])
## Days.for.shipping..real. Days.for.shipment..scheduled. Benefit.per.order
## Min. :0.000 Min. :0.000 Min. :-4274.98
## 1st Qu.:2.000 1st Qu.:2.000 1st Qu.: 7.00
## Median :3.000 Median :4.000 Median : 31.52
## Mean :3.498 Mean :2.932 Mean : 21.98
## 3rd Qu.:5.000 3rd Qu.:4.000 3rd Qu.: 64.80
## Max. :6.000 Max. :4.000 Max. : 911.80
## Sales.per.customer
## Min. : 7.49
## 1st Qu.: 104.38
## Median : 163.99
## Mean : 183.11
## 3rd Qu.: 247.40
## Max. :1939.99
sales_histogram <- function(data) {
ggplot(data, aes(x = Customer.Id, fill = after_stat(x))) +
geom_histogram() +
scale_fill_gradient(low = "blue", high = "red") +
labs(x = "Sales per customer", y = "Count", title = "Distribution of Sales per Customer")
}
sales_histogram(data)
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
# Function to create histogram of delivery status distribution
create_delivery_status_histogram <- function(data) {
ggplot(data, aes(x = Delivery.Status)) +
geom_bar() +
labs(x = "Delivery Status", y = "Count", title = "Delivery Status Distribution")
}
create_delivery_status_histogram(data)
delivery_status_plot <- function(data) {
ggplot(data, aes(x = Delivery.Status)) +
geom_bar(fill = "#69b3a2") +
scale_color_manual(values = c("#E69F00", "#56B4E9", "#009E73")) +
labs(x = "Delivery Status", y = "Count", title = "Delivery Status Distribution")
}
delivery_status_plot(data)
late_delivery_category_plot <- function(data) {
# Filter data based on "Late delivery" status
late_delivery <- data %>%
filter(Delivery.Status == "Late delivery")
# Count the number of late deliveries by Category Name
category_counts <- late_delivery %>%
group_by(Category.Name) %>%
summarise(count = n()) %>%
arrange(desc(count)) %>%
top_n(10)
# Plot the top 10 categories by count of late deliveries
ggplot(category_counts, aes(x = Category.Name, y = count, fill = Category.Name)) +
geom_col() +
labs(x = "Category Name", y = "Count of Late Deliveries", title = "Top 10 Categories by Late Delivery Count") +
theme(axis.text.x = element_text(angle = 45, hjust = 1))
}
late_delivery_category_plot(data)
## Selecting by count
plot_late_delivery_by_country <- function(data) {
# Filter data based on "Late delivery" status
late_delivery <- data %>%
filter(Delivery.Status == "Late delivery")
# Count the number of late deliveries by Order.Country
country_counts <- late_delivery %>%
group_by(Order.Country) %>%
summarise(count = n()) %>%
arrange(desc(count)) %>%
top_n(10)
# Plot the top 10 countries by count of late deliveries
ggplot(country_counts, aes(x = Order.Country, y = count, fill = Order.Country)) +
geom_col() +
labs(x = "Country", y = "Count of Late Deliveries", title = "Top 10 Countries by Late Delivery Count") +
theme(axis.text.x = element_text(angle = 45, hjust = 1))
}
plot_late_delivery_by_country(data)
## Selecting by count
# Function to create boxplot of sales by category name
create_sales_boxplot <- function(data) {
ggplot(data, aes(x = Category.Name, y = Sales, fill = Category.Name)) +
geom_boxplot() +
labs(title = "Category Name vs. Sales")
}
create_sales_boxplot(data)
# Function to create boxplot of late delivery risk by shipping mode
create_delivery_boxplot <- function(data) {
ggplot(data, aes(x = Shipping.Mode, y = Late_delivery_risk, fill = Shipping.Mode)) +
geom_boxplot() +
labs(title = "Shipping Mode vs. Late Delivery Risk")
}
create_delivery_boxplot(data)
# Highest revenue based on Department.
plot_sales_by_department <- function(data) {
# Aggregate sales by department
sales_by_department <- data %>%
group_by(Department.Name) %>%
summarize(total_sales = sum(Sales))
# Create the plot
p <- ggplot(sales_by_department, aes(x = Department.Name, y = total_sales, fill = Department.Name,
text = paste("Department: ", Department.Name, "<br>", "Sales: $",
scales::comma(total_sales)))) +
geom_bar(stat = "identity") +
labs(title = "Total Sales by Department", x = "Department", y = "Sales") +
theme(axis.text.x = element_text(angle = 90, vjust = 0.5, hjust = 1))
# Convert the plot to Plotly
ggplotly(p)
}
plot_sales_by_department(data)
top_10_orders_by_country <- function(data) {
# calculate the count of orders by Order.Country
orders_by_country <- data %>%
group_by(Order.Country) %>%
summarize(count = n()) %>%
arrange(desc(count)) %>%
slice(1:10)
# create the plot
p <- ggplot(orders_by_country, aes(x = Order.Country, y = count, fill = Order.Country, text = paste("Country: ", Order.Country, "<br>", "Orders: ", count))) +
geom_bar(stat = "identity") +
labs(title = "Top 10 Order Countries by Customer Orders") +
xlab("Order Country") +
ylab("Customer Orders") +
theme(axis.text.x = element_text(angle = 90, vjust = 0.5, hjust=1))
# convert the plot to plotly
ggplotly(p)
}
top_10_orders_by_country(data)
plot_order_region_count <- function(data) {
# create a data frame with the count of orders by order region
order_region_count <- data %>%
group_by(Order.Region) %>%
summarise(Count = n()) %>%
arrange(desc(Count))
# create the plot
plot <- ggplot(order_region_count, aes(x = Order.Region, y = Count, fill = Order.Region, text = paste("Order Region: ", Order.Region, "<br>", "Order Count: ", Count))) +
geom_bar(stat = "identity") +
labs(title = "Order Regions by Count of Orders from Customers") +
xlab("Order Region") +
ylab("Order Count") +
theme(axis.text.x = element_text(angle = 90, vjust = 0.5, hjust=1)) +
scale_fill_viridis_d()
# convert the plot to plotly
ggplotly(plot)
}
plot_order_region_count(data)
# get the top 20 customers who did the highest sales.
top_customers_sales_plot <- function(data) {
# create a data frame with sales per customer
sales_per_customer <- data %>%
group_by(Customer.Id) %>%
summarise(total_sales = sum(Sales)) %>%
arrange(desc(total_sales))
# get the top 20 customers who did the highest sales.
top_customers <- head(sales_per_customer, 20)
# create a new column with the combined first and last name of each customer
top_customers <- top_customers %>%
left_join(data %>% select(Customer.Id, Customer.Fname, Customer.Lname), by = "Customer.Id") %>%
mutate(CustomerName = paste(Customer.Fname, Customer.Lname, sep = " "))
# create the plot
plot <- ggplot(top_customers, aes(x = reorder(CustomerName, -total_sales), y = total_sales, fill = CustomerName, text = paste("Customer Name: ", CustomerName, "<br>", "Total Sales: $", total_sales))) +
geom_bar(stat = "identity") +
labs(title = "Top 20 Customers by Sales") +
xlab("Customer Name") +
ylab("Total Sales") +
theme(axis.text.x = element_text(angle = 90, vjust = 0.5, hjust=1))
# convert the plot to plotly
ggplotly(plot)
}
top_customers_sales_plot(data)
generate_sales_profit_plot <- function(data) {
# Convert order date to date format
data$order.date..DateOrders. <- as.Date(data$order.date..DateOrders., format = "%m/%d/%Y %H:%M")
# Create data for year dropdown menu
years <- data %>%
group_by(year = lubridate::year(order.date..DateOrders.)) %>%
summarise(total_sales = sum(Sales), total_profit = sum(Order.Profit.Per.Order))
# Create data for month dropdown menu
months <- data %>%
group_by(month = lubridate::month(order.date..DateOrders., label = TRUE),
year = lubridate::year(order.date..DateOrders.)) %>%
summarise(total_sales = sum(Sales), total_profit = sum(Order.Profit.Per.Order))
# Create data for quarter dropdown menu
quarters <- data %>%
group_by(quarter = quarters(order.date..DateOrders.),
year = lubridate::year(order.date..DateOrders.)) %>%
summarise(total_sales = sum(Sales), total_profit = sum(Order.Profit.Per.Order))
# Create sales and profit plot
generate_plot <- function(input_sales_profit, input_year, input_month_quarter) {
filtered_data <- if (input_month_quarter == "month") {
months %>%
filter(year == input_year)
} else {
quarters %>%
filter(year == input_year)
}
if (input_sales_profit == "Sales") {
ggplot(filtered_data, aes(x = get(input_month_quarter), y = total_sales)) +
geom_bar(stat = "identity") +
labs(title = paste("Total Sales by", input_month_quarter, "in", input_year),
x = input_month_quarter, y = "Sales")
} else {
ggplot(filtered_data, aes(x = get(input_month_quarter), y = total_profit)) +
geom_bar(stat = "identity") +
labs(title = paste("Total Profit by", input_month_quarter, "in", input_year),
x = input_month_quarter, y = "Profit")
}
}
return(generate_plot)
}
sales_profit_plot <- generate_sales_profit_plot(data)
## `summarise()` has grouped output by 'month'. You can override using the
## `.groups` argument.
## `summarise()` has grouped output by 'quarter'. You can override using the
## `.groups` argument.
# Generate sales plot for year 2016 monthly and quarterly
sales_profit_plot("Sales", 2015, "month")
sales_profit_plot("Sales", 2015, "quarter")
# Generate sales plot for year 2016 monthly and quarterly
sales_profit_plot("Sales", 2016, "month")
sales_profit_plot("Sales", 2016, "quarter")
# Generate sales plot for year 2017 monthly and quarterly
sales_profit_plot("Sales", 2017, "month")
sales_profit_plot("Sales", 2017, "quarter")
# Generate sales plot for year 2016 monthly and quarterly
sales_profit_plot("Sales", 2018, "month")
sales_profit_plot("Sales", 2018, "quarter")
